Open Reality

Live monocular SLAM · no LiDAR

Open Reality

Walk through a space with your phone. A dense 3D map assembles in real time — and you can ask it questions.

The point cloud behind this text is a real capture — drag it.

Field recordings

Scenes you can explore

Every capture below was recorded on a phone and reconstructed by the live pipeline. Run any of them from your dashboard to replay the full system — mapping, detection, and the spatial agent.

Family Home — sample scene stillresidential survey

Family Home

A walk from entryway to kitchen becomes a dense 3D map — seating, appliances, and storage indexed as the camera moves.

Research Building — sample scene stillfacilities survey

Research Building

One pass through a university building's hallways: workstations, whiteboards, and safety equipment, all tracked in place.

Crime Scene — sample scene stillforensic documentation

Crime Scene

Evidence markers and disturbed objects documented with their spatial relationships intact — a scene you can re-walk later.

Flooded Street — sample scene stilldisaster response

Flooded Street

A flood-damaged street surveyed for structural damage, displaced objects, and roadway hazards in a single walk-through.

Earthquake Aftermath — sample scene stilldamage assessment

Earthquake Aftermath

Urban damage assessment: debris fields, failed infrastructure, and blocked pathways mapped from one continuous pass.

Hackathon Venue — sample scene stillevent venue

Hackathon Venue

A live event space mapped in motion — seating, collaborative work areas, and circulation routes captured as they're used.

Second Interior — sample scene stillinterior survey

Second Interior

A second residential survey focused on layout and usage patterns — furniture, electronics, and storage, room by room.

Our Workspace — sample scene stillteam workspace

Our Workspace

The team's own table, scanned mid-build — laptops, tools, and the reconstruction itself running on screen.

Our work

What happens under the hood

Dense SLAM, in real time

A feed-forward transformer predicts dense depth and camera pose straight from the monocular video stream — no LiDAR, no depth sensor. Submaps are stitched on the SL(4) manifold and optimized with GTSAM, so the map stays consistent even when your path crosses itself.

VGGT-SLAM 2.0 · SL(4) · GTSAM · loop closure

Detection without a label set

Tell the system what matters in plain language instead of picking from a fixed list of classes. Open-set detection segments the objects you asked for and anchors them in the 3D map, where they keep their positions as the scan grows.

CLIP · SAM3 · open-set 3D detection

An agent that knows where things are

An autonomous spatial agent connects your goal to the live geometry: it plans what to track, runs deep scans on regions of interest, and answers questions grounded in what the camera has actually seen — during the scan and after it.

autonomous missions · grounded Q&A · scene reports

Any phone, no app

Capture runs in the mobile browser — open a link, point the camera, walk. The heavy lifting happens on a dedicated GPU session in the cloud, streamed back to you as the map assembles.

mobile browser capture · dedicated GPU session

Begin

Open your reality.

A few minutes of walking is enough to map a space you can revisit, search, and question.

Open RealityVGGT-SLAM 2.0 · SL(4) · CLIP · SAM3